Comfyui_joytag

Comfyui_joytag
★ 66

图像标注Danbooru性友好/包容多风格兼容
Comfyui_joytag 节点：基于 JoyTag 的图像自动标注器，生成 Danbooru 风格标签，强调性友好与包容，兼容插画与照片。
💡 为插画、摄影或生成图像自动生成Danbooru标签，便于分类检索。
🍴 8 Forks💻 Python🔄 2024-05-22
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/6862a2001521
📦 requirements.txt
#
torch>=2.0.1,<3.0.0
transformers>=4.36.2
#
torchvision>=0.15.2
einops>=0.7.0
safetensors>=0.4.1
pillow>=9.4.0
cfc502ede5701fdcaf83f6f71c91747
📄 README

Comfyui_joytag

JoyTag is a state of the art AI vision model for tagging images, with a focus on sex positivity and inclusivity. It uses the Danbooru tagging schema, but works across a wide range of images, from hand drawn to photographic.

  • Download and put it under the custom_nodes node
  • Install dependencies requirements.txt
  • Change the name to “Comfyui_joytag”
  • Download the weight and put it under checkpoints

    • https://huggingface.co/fancyfeast/joytag/tree/main